Learning a Scanning Understanding for "Real-world" Library Categorization

This paper describes a general architecture SCAN for hybrid symbolic connectionist processing of natural language phrases. SCAN's architecture shows how learned connectionist domain-dependent semantic representations can be combined with encoded symbolic syntactic representations. Within this general architecture we focus on a connectionist model for semantic classication based on a scanning understanding of phrases. We specify strategies at the top-most theory level and we show how these strategies are realized in a recurrent connectionist plausibility network at the underlying representation level. In particular, this model demonstrates that a recurrent connectionist network can learn a semantic memory model for phrase classication based on a scanning understanding.

@InProceedings{Wer92a,
 	 author =  {Wermter, Stefan},
 	 title = {Learning a Scanning Understanding for  "Real-world" Library Categorization},
 	 booktitle = {Proceedings of the Conference on Applied Natural Language Processing},
 	 journal = {None},
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {251--252},
 	 year = {1992},
 	 month = {}
 	 publisher = {None},
 	 doi = {}
 }